AgriEngineering, Volume 3, Issue 2 (June 2021) – 20 articles

At the CREA research facility of Treviglio (Bergamo, Italy), to provide farmers with valuable hints for the transition from conventional to precision agriculture, information on crop production dynamics (Maize and Triticale) has been obtained using real-time soil mapping (resistivity technique) and production quality and quantity monitoring with a commercial yield mapping apparatus. The geostatistical processing of data resulted in the same zoning for Triticale, meaning that the characteristics of soil influenced crop behavior more than the variability resulting from other factors, which suggests that improvements in product yields can be planned and achieved acting, for instance, on variable rate distribution of fertilizers. The importance of the acquired data can help farmers to manage factors that are external to their plots of land. Full article

Low-cost GPS (Global Positioning System) speed sensors have been available to quantify vehicle speed on different platforms including agricultural tractors in precision agriculture applications such as yield monitoring, variable rate fertilizer and pesticide applications. One of the advances in low-cost GPS receivers is the higher data update frequencies. However, we found no studies on the accuracy of low-cost GPS speed sensors with different update frequencies, especially under variable speed conditions. Thus, this work investigated the effect of the update frequency on the accuracy of low-cost GPS speed sensors under both constant and varying speed conditions. Three GPS speed sensors with update frequencies of 1 Hz, 5 Hz and 7 Hz (GPS1Hz, GPS5Hz and GPS7Hz) were simultaneously tested under the same conditions. A total of 144 tests were conducted on three different days and at three different times of each day with four speed levels and four repetitions. The percent errors were found to be up to 2.3%, 1.8% and 1.4% at constant speeds; up to −47%, −16% and −12% at the increasing speeds and 24%, 6% and 5% at the decreasing speeds, depending on the acceleration and deceleration levels, for GPS1Hz, GPS5Hz and GPS7Hz, respectively. The differences among the error values of the GPS speed sensors were found to be statistically significant (p < 0.05). The GPS speed sensors with higher update frequencies (5 and 7 Hz) provided higher accuracy compared to the one with lower frequency (1 Hz), particularly in the case of higher acceleration conditions. In sum, low-cost GPS speed sensors with higher update frequencies should be used for better accuracy, especially in variable speed conditions. Full article

Jute is the golden fiber of Bangladesh, but its production is declining due to the involvement of higher production and processing costs, where a major portion of the cost is needed for fiber extraction. Labor unavailability and increasing labor cost have led to higher jute fiber production cost. To address these issues, this study looks at the development of a power-operated and cost-effective fiber extraction machine aiming at reducing the production cost. The study was conducted at the Rangpur regional office premises of Practical Action in Bangladesh, and the developed machine was branded as “Aashkol”, which had the following major parts: a feeding tray, a primary extraction roller, a secondary extraction roller, grabbing rollers, fiber collection stand, base frame, protection cover, and a spring-loaded tray under the primary extraction roller. The Aashkol can extract green ribbon from the jute stem, but jute sticks were broken down into smaller pieces (3–6 cm). The performance evaluation of the machine was conducted using different types of jute (Deshi, Kenaf, and Tossa) and compared with another jute extraction machine (KP model, introduced by Karupannya Rangpur Ltd.). The Aashkol-based extraction and improved retting systems were also evaluated and compared with traditional jute extraction systems. The jute stem input capacity (4.99 t h⁻¹) of the Aashkol was 47.6% higher than the KP model (3.38 t h⁻¹). Compared with the traditional system, across jute types, the Aashkol produced a 9% higher fiber yield and saved 46% retting time. Overall, the Aashkol reduced 90% of the labor requirement and saved 11.6 USD t⁻¹ in jute fiber extraction and retting than the traditional method. Full article

The genetic development of the commercial broiler has led to body misconfiguration and consequent walking disabilities, mainly at the slaughter age. The present study aimed to identify broiler locomotion ability using image analysis automatically. A total of 40 broilers that were 40 d old (male and female) were placed to walk on a specially built runway, and their locomotion was recorded. An image segmentation algorithm was developed, and the coordinates of the bird’s center of mass were extracted from the segmented images for each frame analyzed, and the unrest index (UI) was applied. We calculated the center of mass’s movement of the broiler walking lateral images capturing the bird’s displacement speed in the onward direction. Results indicated that broiler walking speed on the runway tends to decrease with the increase of the gait score. The locomotion did not differ between males or females. The proposed algorithm was efficient in predicting the broiler gait score based on their displacement speed. Full article

The present study investigates the effect of intercropping (maize-cowpea, maize-okra, maize-okra-cowpea, okra-cowpea) compared to insecticide application on the level of infestation of insect pests and the final yield of maize, cowpea and okra. Field experiments were conducted during the 2016 and 2017 cropping seasons in the Guinean Savannah (Dang-Ngaoundere) and Sudano Sahelian (Gouna-Garoua) agro-ecological zones in Cameroon. Our experimental design was a split plot arrangement in a randomized complete block with four replications. The main factor was assigned to the use of insecticide (Cypermethrin) and sub plots were devoted for cropping systems. We compared the efficiency of intercropping to that of Cypermethrin application on the Yield of maize, cowpea and okra as influenced by insect pest damages. The comparison of monocropped sprayed by Cypermethrin to unsprayed showed that, in Dang, insect pests reduced maize yield by 37% and 24% in 2016 and 2017, respectively, whereas in Gouna, it was lower than 8% during the both years. Reduction in seed yield by insect pests on cowpea in Dang represented 47% and 50% in 2016 and 2017, respectively, whereas in Gouna, it was 55% and 63% in 2016 and 2017, respectively. For okra, insect pests reduced okra fruit yield by 25% and 44% in Dang and 23% and 28% in Gouna, respectively, in 2016 and 2017. Crop yield was lower in intercropping compared to monoculture due to competition of plants in association on different resources. Considering the total yields obtained from each intercropping, intercropping trials resulted generally in higher yields compared to mono-culture (LER > 1) in both sites and years but the respective yields were quite different. On the basis of the results obtained, we recommend maize-cowpea intercropping as a sustainable solution to reduce the infestation level of their pest insects. Full article

To reduce human drudgery and the risk of labor shortages in the Asian developing countries, the appropriate introduction of agricultural machinery, especially combine harvesters, is an urgent task. Custom hiring services (CHSs) are expected to contribute to making paddy harvesters prevalent in developing countries; however, the economic performance has been rarely quantified. The study was carried out to precisely evaluate the machine performance attributes of medium and large combine harvesters using the real-time kinematic (RTK) global navigation satellite system (GNSS) and to estimate the economic performance of CHSs of paddy harvesters in Japan, as a typical case of Asian countries. The financial profitability was evaluated by four major indicators: net present value, benefit–cost ratio, internal rate of return, and payback period. The financial indicators showed that both types of harvester could be considered financially viable. Thus, the investment in combine harvesters can be highly profitable for CHS business by a local service provider and custom-hire entrepreneur, providing a great opportunity to use a combine harvester without initial investment by general farmers. The findings demonstrated the high feasibility of CHSs of paddy harvesters in Japan, while they highlighted that further study is needed to estimate the feasibility of CHS in the other Asian developing countries. Full article

Automation continues to play a greater role in agricultural production with commercial systems now available for machine vision identification of weeds and other pests, autonomous weed control, and robotic harvesters for fruits and vegetables. The growing availability of autonomous machines in agriculture indicates that there are opportunities to increase automation in cotton production. This article considers how current and future advances in automation has, could, or will impact cotton production practices. The results are organized to follow the cotton production process from land preparation to planting to within season management through harvesting and ginning. For each step, current and potential opportunities to automate processes are discussed. Specific examples include advances in automated weed control and progress made in the use of robotic systems for cotton harvesting. Full article

US cotton producers are motivated to optimize planter performance to ensure timely and uniform stand establishment early in the season, especially when planting in sub-optimal field conditions. Field studies were conducted in 2017, 2018 and 2019 to evaluate the effect of seeding depth and planter downforce on crop emergence and yield in cotton planted in different soil moisture conditions. Field conditions representative of dry, normal and wet soil moisture conditions were attained by applying 0, 1.27 and 2.54 cm of irrigation within the same field. Two cotton cultivars (representing a small-seeded and a large-seeded cultivar, 9259–10,582 and 11,244–14,330 seeds kg⁻¹, respectively), were planted at seeding depths of 1.3, 2.5 and 3.8 cm with each seeding depth paired with three different planter downforces of 0, 445 and 890 N in each block. Cotton was planted in plots that measured 3.66 m (four-rows) wide by 10.67 m long. Results indicated that crop emergence was affected by the seeding depth across most field conditions and higher crop emergence was observed in the large-seeded cultivar at 1.3 and 3.8 cm seeding depths in dry and wet field conditions, respectively. Lint yield was also higher for the large-seeded cultivar at the 3.8 cm seeding depth across all field conditions in 2017, and in dry field conditions in 2018. Planter downforce effect on crop emergence varied among the cultivars where the large-seeded cultivar exhibited higher crop emergence than the small-seeded cultivar at 445 and 890 N downforce. Planter downforce of 445 N yielded greater than the 0 and 890 N treatment in dry field conditions in 2017. The study results suggest that matching planter depth and downforce settings for prevalent soil moisture conditions at planting along with appropriate cultivar selection can help in achieving optimal emergence and yield in cotton. Full article

A series of experiments were conducted to measure and quantify the yield, dry matter content, sugars content, and nitrates content of grass intended for ensilement. These experiments took place in the East Midlands of Ireland during the Spring, Summer, and Autumn of 2019. A bespoke sensor rig was constructed; included in this rig was a hyperspectral radiometer that measured a broad spectrum of reflected natural light from a circular spot approximately 1.2 m in area. Grass inside a 50 cm square quadrat was manually collected from the centre of the circular spot for ground truth estimation of the grass qualities. Up to 25 spots were recorded and sampled each day. The radiometer readings for each spot were automatically recorded onto a laptop that controlled the sensor rig, and ground truth measurements were made either on-site or within 24 h in a wet chemistry laboratory. The collected data was used to build Partial Least Squares Regression (PLSR) predictive models of grass qualities from the hyperspectral dataset, and it was found that substantial relationships exist between the spectral reflectance from the grass and yield (r² = 0.62), dry matter % (r² = 0.54), sugar content (r² = 0.54) and nitrates (r² = 0.50). This shows that hyperspectral reflectance data contains substantial information about key grass qualities and can form part of a broader holistic data-driven approach to provide accurate and rapid predictions to farmers, agronomists, and agricultural contractors. Full article

Plants are a major source of food for the world population. Plant diseases contribute to production loss, which can be tackled with continuous monitoring. Manual plant disease monitoring is both laborious and error-prone. Early detection of plant diseases using computer vision and artificial intelligence (AI) can help to reduce the adverse effects of diseases and also overcome the shortcomings of continuous human monitoring. In this work, we propose the use of a deep learning architecture based on a recent convolutional neural network called EfficientNet on 18,161 plain and segmented tomato leaf images to classify tomato diseases. The performance of two segmentation models i.e., U-net and Modified U-net, for the segmentation of leaves is reported. The comparative performance of the models for binary classification (healthy and unhealthy leaves), six-class classification (healthy and various groups of diseased leaves), and ten-class classification (healthy and various types of unhealthy leaves) are also reported. The modified U-net segmentation model showed accuracy, IoU, and Dice score of 98.66%, 98.5%, and 98.73%, respectively, for the segmentation of leaf images. EfficientNet-B7 showed superior performance for the binary classification and six-class classification using segmented images with an accuracy of 99.95% and 99.12%, respectively. Finally, EfficientNet-B4 achieved an accuracy of 99.89% for ten-class classification using segmented images. It can be concluded that all the architectures performed better in classifying the diseases when trained with deeper networks on segmented images. The performance of each of the experimental studies reported in this work outperforms the existing literature. Full article

Press-wheels are wheels designed to compact the soil above seeds in the “seed cover” region. Soil compaction, produced by the press-wheels of seeders, affects seedling emergence and early plant growth. The Discrete Element Method (DEM) was used to model the amount of soil compaction from a press-wheel with varying down forces. The model was used to predict sinkage and rolling resistance of the press-wheel. The model results were validated with data from soil bin tests of the press-wheel in a sandy loam soil under varying soil moisture content levels (low, medium, and high). The sinkage results from the soil bin tests were 27.7, 26.7, and 25.2 mm for the low, medium, and high soil moisture content levels, respectively. The corresponding rolling resistances obtained from the tests were 104.4, 89.9, and 113.6 N. The press-wheel model adequately predicted the sinkage and rolling resistance for each soil moisture content level with overall Relative Mean Errors (RME) ranging from 13 to 23%. Additional simulation results show that average peak soil stresses across the three soil moisture contents at a depth of 0.12 m were 22,466.7, 8700.0, and 6900.0 Pa for vertical, horizontal, and lateral directions, respectively. The results enhance the understanding of the dynamics of the soil–press-wheel interaction and provided useful information for seeder press-wheel design. Full article

The objective of this paper was to quantify the economic and environmental effects of changing a dairy farm’s milking start times. Changing morning and evening milking start times could reduce both electricity costs and farm electricity related CO₂ emissions. However, this may also involve altering farmer routines which are based on practical considerations. Hence, these changes need to be quantified both in terms of profit/emissions and in terms of how far these milking start times deviate from normal operations. The method presented in this paper optimized the combination of dairy farm infrastructure setup and morning and evening milking start times, based on a weighting variable (α) which assigned relative importance to labor utilization, farm net profit and farm electricity related CO₂ emissions. Multi-objective optimization was utilized to assess trade-offs between labor utilization and net profit, as well as labor utilization and electricity related CO₂ emissions. For a case study involving a 195 cow Irish dairy farm, when the relative importance of maximizing farm net profit or minimizing farm electricity related CO₂ emissions was high, the least common milking start times (06:00 and 20:00) were selected. When the relative importance of labor utilization was high, the most common milking start times (07:00 and 17:00) were selected. The 195 cow farm saved €137 per annum when milking start times were changed from the most common to the least common. Reductions in electricity related CO₂ emissions were also seen when the milking start times were changed from most common to least common. However, this reduction in emissions was primarily due to the addition of efficient and renewable technology to the farm. It was deduced that the monetary and environmental benefits of altering farmer milking routines were unlikely to change normal farm operating procedures. Full article

Fermentative digestion by ruminant livestock is one of the main ways enteric methane enters the atmosphere, although recent studies have identified that including red macroalgae as a feed ingredient can drastically reduce methane produced by cattle. Here, we utilize ecological modelling to identify suitable sites for establishing aquaculture development to support sustainable agriculture and Sustainable Development Goals 1 and 2. We used species distributions models (SDMs) parameterized using an ensemble of multiple statistical and machine learning methods, accounting for novel methodological and ecological artefacts that arise from using such approaches on non-native and cultivated species. We predicted the current distribution of two Asparagopsis species to high accuracy around the coast of Ireland. The environmental drivers of each species differed depending on where the response data was sourced from (i.e., native vs. non-native), suggesting that the length of time A. armata has been present in Ireland may mean it has undergone a niche shift. Subsequently, researchers looking to adopt SDMs to support aquaculture development need to acknowledge emerging conceptual issues, and here we provide the code needed to implement such research, which should support efforts to effectively choose suitable sites for aquaculture development that account for the unique methodological steps identified in this research. Full article

The recent availability of soybean cultivars with resistance to dicamba herbicide has increased the risk of injury in susceptible cultivars, mainly as a result of particle drift. To predict and identify the damage caused by this herbicide requires great accuracy. The objective of this work was to evaluate the injury caused by the simulated drift of dicamba on soybean (nonresistant to dicamba) plants assessed visually and using the Triangular Greenness Index (TGI) from images obtained from Remotely Piloted Aircraft (RPA). The study was conducted in a randomized complete block design with four replications during the 2019/2020 growing season, and the treatments consisted of the application of six doses of dicamba (0, 0.28, 0.56, 5.6, 28, and 112 g acid equivalent dicamba ha⁻¹) on soybean plants at the third node growth stage. For the evaluation of treatments using the TGI technique, spectral data acquired through a Red Green Blue (RGB) sensor attached to an RPA was used. The variables studied were the visual estimation of injury, TGI response at 7 and 21 days after application, plant height, and crop yield. The exposure to the herbicide caused a reduction in plant height and crop yield. Vegetation indices, such as TGI, have the potential to be used in the evaluation of injury caused by dicamba, and may be used to cover large areas in a less subjective way than visual assessments. Full article

Spraying pesticides using air induction nozzles is a well-known method to reduce drift. These drift-reducing nozzles have been tested on many different tree crops (such as apples, citrus, and grapes), but we are still lacking information on their utilization on hazelnut (Corylus avellana L.) groves, although hazelnut is a major nut crop in Italy, and in recent years its cultivated area has been constantly growing. This paper reports a comparison between treatments carried out with cone and flat-fan low-drift nozzles versus two conventional nozzles. The distribution quality, the number of droplets per cm² of the target area, and the drift in non-target trees adjacent to those treated were evaluated by analyzing the impact of the droplets on water-sensitive papers placed on the tree canopies. The results show that because no significative differences in terms of application quality were found between the tested nozzles, low-drift nozzles can be a good alternative to the standard nozzles to reduce the drift of pesticide applications in hazelnuts without altering the chosen distribution of the pesticide. Full article

Time spent feeding by grazing cattle is an important predictor of intake and feed efficiency. This study examined the use of automatic supplement weighing (ASW) units for monitoring voluntary access of breeding cows (n = 430) to mineral block supplements in an extensive rangeland of northern Australia. The ASW units (n = 10) were located within each of experimental sites (5 units per site; Bore and Eldons). Over the 62 days of data collection, 85%, 13%, and 2% of cows spent <600, 600–1200, >1200 min accessing supplements, respectively, with between-animal variation (CV) of 107%. A total of 133 cows visited both sites while 142 and 155 cows visited only Bore and Eldons, respectively. Most visits (80–90%) were recorded during the day (800–1700 h), 7–17% during the night (1800–2300 h), and 3% during the dawn (0–700 h). Time spent accessing supplements differed between ASW units across the two sites (p < 0.001) and varied according to the day of visits (p < 0.001). There was a significant relationship between time spent at the ASW units and supplement intake on a herd basis (p < 0.001; R²_adj = 0.70). The results showed that the ASW units were capable of monitoring access to mineral block supplements that may reflect the supplement intake of rangeland cattle. Full article

The US cotton industry provided over 190,000 jobs and more than $28 billion total economic contributions to the United States in 2012. The US is the third-largest cotton-producing country in the world, following India and China. US cotton producers have been able to stay competitive with countries like India and China by adopting the latest technologies. Despite the success of technology adoption, there are still many challenges, e.g., increased pest resistance, mainly glyphosate resistant weeds, and early indications of bollworm resistance to Bt cotton (genetically modified cotton that contains genes for an insecticide). Commercial small unmanned ground vehicle (UGV) or mobile ground robots with navigation-sensing modality provide a platform to increase farm management efficiency. The platform can be retrofitted with different implements that perform a specific task, e.g., spraying, scouting (having multiple sensors), phenotyping, harvesting, etc. This paper presents a proof-of-concept cotton harvesting robot. The robot was retrofitted with a vacuum-type system with a small storage bin. A single harvesting nozzle was used and positioned based on where most cotton bolls were expected. The idea is to create a simplified system where cotton bolls′ localization was undertaken as a posteriori information, rather than a real-time cotton boll detection. Performance evaluation for the cotton harvesting was performed in terms of how effective the harvester suctions the cotton bolls and the effective distance of the suction to the cotton bolls. Preliminary results on field test showed an average of 57.4% success rate in harvesting locks about 12 mm from the harvester nozzle. The results showed that 40.7% was harvested on Row A while 74.1% in Row B for the two-row test. Although both results were promising, further improvements are needed in the design of the harvesting module to make it suitable for farm applications. Full article

The prediction of rice yields plays a major role in reducing food security problems in India and also suggests that government agencies manage the over or under situations of production. Advanced machine learning techniques are playing a vital role in the accurate prediction of rice yields in dealing with nonlinear complex situations instead of traditional statistical methods. In the present study, the researchers made an attempt to predict the rice yield through support vector regression (SVR) models with various kernels (linear, polynomial, and radial basis function) for India overall and the top five rice producing states by considering influence parameters, such as the area under cultivation and production, as independent variables for the years 1962–2018. The best-fitted models were chosen based on the cross-validation and hyperparameter optimization of various kernel parameters. The root-mean-square error (RMSE) and mean absolute error (MAE) were calculated for the training and testing datasets. The results revealed that SVR with various kernels fitted to India overall, as well as the major rice producing states, would explore the nonlinear patterns to understand the precise situations of yield prediction. This study will be helpful for farmers as well as the central and state governments for estimating rice yield in advance with optimal resources. Full article

Collection of plant inventory (i.e., count, grade, plant size, yield) data is time-consuming, costly, and can be inaccurate. In response to increasing labor costs and shortages, there is an increased need for the adoption of more automated technologies by the nursery industry. Growers, small and large, are beginning to adopt technologies (e.g., plant spacing robots) that automate or augment certain operations, but greater strides must be taken to integrate next-generation technologies into these challenging unstructured agricultural environments. The main objective of this work is to demonstrate merging specific ground and aerial-based technologies (Radio Frequency Identification (RFID), and small Unmanned Aircraft System (sUAS)) into a holistic systems approach to address the specific need of moving toward automated on-demand plant inventory. This preliminary work focuses on evaluating different RFID tags with respect to their distance and orientation to the RFID reader. Fourteen different RFID tags, five distances (1.5 m, 3.0 m, 4.5 m, 6.0 m, and 7.6 m), and four tag orientations (the front of the tag (UP), back of the tag (DN), tag at sideways left (SL), and tag at sideways right (SR)) were assessed. Results showed that the tag upward orientation resulted in the highest scanning total for both the laboratory and field experiments. Two orientations (UP and SR) had significant effect on the scan total of tags. The distance between the reader and the tags at 1.5 m and 6.0 m did not significantly affect the scanning efficiency of the RFID system in horizontally fixed (p-value > 0.05) position regardless of tags. Different tag designs also produced different scan totals. Overall, since most of the tags were scanned at least once (except for Tag 6F), it is a very promising technology for use in nursery inventory data acquisition. This work will create a unique inventory system for agriculture where locations of plants or animals will not present a barrier as the system can easily be mounted on a drone. Although these experiments are focused on inventory in plant nurseries, results for this work has potential for inventory management in other agricultural sectors. Full article

A multi-bale handling unit offers an advantage for the efficient hauling of round bales. Two empty racks on trailers are left at a satellite storage location for loading while a truck tractor delivers two loaded racks to the biorefinery, thus uncoupling the loading and hauling operations and increasing the efficiency of both. The projected 10 min trailer exchange time equals the projected 10 min unload time at the biorefinery achieved by lifting off the two full racks and replacing them with two empties, a technology adapted from the container shipping industry. A concept is presented for a bale loader that latches onto the rack/trailer and loads bales into the bottom tier chambers. This machine will load 10 bales into the rack on the front trailer by attaching on to the front of the trailer and 10 bales into the rear trailer by attaching onto the rear. A telehandler removes bales from single-layer storage and places them in the bale loader to load the bottom tier compartments. The top tier compartments are loaded directly from the top. Expectations are that an experienced operator can average 9 loads in a 10 h workday, and load-out cost is estimated as 3.61 USD/Mg, assuming the average achieved load-out productivity over annual operation is 60% of optimum productivity (24 Mg/h) equal to 14.4 Mg/h. Cost increases to 4.81 USD/Mg when the productivity factor drops to 45%, and cost is 3.09 USD/Mg for a factor of 70%. Full article